© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 9822
    Prev
    Next
    INDEX
    Explanations

    instances of the word "feathers."

    oai_token-act-pair · gpt-3.5-turbo

    references to feathers and foil materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iazep
    -0.73
    Benz
    -0.70
    birth
    -0.70
    reme
    -0.70
    task
    -0.68
     Keynes
    -0.68
    venture
    -0.68
    claim
    -0.67
    stream
    -0.67
    edit
    -0.65
    POSITIVE LOGITS
     feathers
    1.10
     foil
    1.06
     suscept
    0.84
     insulation
    0.82
    ï¸
    0.81
    åħī
    0.80
    heet
    0.79
    utical
    0.78
    ickr
    0.78
     flakes
    0.78
    Activations Density 0.023%

    No Known Activations